Thread

Claude Code now reads AGENTS.md if there is no Claude.md

741 points · 285 comments · datadrivenangel

TomGarden · 1789766461 · focus · HN ↗
Caught myself about to praise this, but it's the absolute bare minimum.
Time to delete the symlinks
1. eleventen · 1789771616 · focus · HN ↗
  Anthropic in 2025: We can use our dominant market position to degrade the harness experiences of our competitors because they will never adopt CLAUDE.md
  Anthropic in 2026: We are losing our market position. Users who adopted other harnesses have a degraded Claude Code experience because it doesn't recognize their AGENTS.md
  1. armanckeser · 1789772462 · focus · HN ↗
    Sounds like free market at work to me. I am just glad there is quite a lot of competition in a field that I would have assumed would have huge costs of entry
    edoceo · 1789778090 · focus · HN ↗
    Building small models is a lower barrier. Think of something like to just train on a corpus of internal corporate data. I've see some small models that do this. It's like a super RAG thing. I think more of that will happen. Excited to see a SLM vendor emerge.
  2. EA-3167 · 1789773796 · focus · HN ↗
    The walls are closing in and the president is gleefully lighting fires he has no intention of putting out. There's a reason they're rushing like mad to an IPO, but as we saw with OpenAI it's easier said than done when your business model is "Lose tons of money to eventually maybe dominate a market with the moat we don't have, but trust us AI is huge give us trillions."
    the_gipsy · 1789775271 · focus · HN ↗
    With the "let's stop AI now" statements, can it really be said that they're rushing to an IPO?
    TuxSH · 1789776378 · focus · HN ↗
    > "let's stop AI now"
    Pausing AI training would benefit them a lot, as inference is insanely profitable (> 50% margins with maximum demand, afaik)
    EA-3167 · 1789785017 · focus · HN ↗
    Basically asking the government to hobble the competition so they can IPO before the music stops.
  3. mitxela · 1789785940 · focus · HN ↗
    Pretty typical capitalist moves.
    odjeifnejdjej · 1789827959 · focus · HN ↗
    > typical
    Cynical. The word is cynical.
    mitxela · 1789837952 · focus · HN ↗
    No, cynical is what we should be about capitalism.
2. fnordpiglet · 1789776613 · focus · HN ↗
  My view is at the end of 35 years in the industry the current wave of “software” and “systems” engineering coming out of the AI harness community is pretty garbage. But web technology and distributed systems followed a very similar arc, as did protocols and memory management; and microcode before them. But it feels like this is particularly bad because the mistakes being made are plainly obvious to the grey heads who have been here a while. As opposed to before when mistakes were in new domains being explored, these are mistakes made before and have good solutions to.
  I feel people too readily blame the LLMs themselves for this, but I’ve found LLMs know the history of computing thought evolution better than anyone I’ve ever encountered. Once you push them in the right direction, ground them in the philosophy of thought of hard won engineering ideas, they are astoundingly precise and accurate in their read and application (keeping every session grounded is the trick!). So it’s not the machines making these same mistakes with ready conceptual frameworks around them, it’s the 22 year old gatekeepers dashing head first into wall after wall, when we painstakingly built the door two feet to the left about the time they were gestating.
  1. odjeifnejdjej · 1789827885 · focus · HN ↗
    > but I’ve found LLMs know the history of computing thought evolution better than anyone I’ve ever encountered
    …
    Yeah… that’s… pretty much how these LLMs work and their main selling point, actually. Not sure what the “I’m such a greybeard with 350 years worth of experiencie” preamble gets you here besides just making you look like you barely understand what you are talking about.
    fnordpiglet · 1789831398 · focus · HN ↗
    Because, knowing what to induce in its behavior is the key - by understanding things like Postels law, I can direct the agentic loop towards patterns of development that avoid the cascade of issues that seem endemic in modern agentic harnesses.
    In fact, this is a key insight, so it’s surprising you didn’t get the punchline. Trying to build things in a new way on a machine composed of the corpus of all the old ways is stupid. By eliciting the corpus of tried and true methods over the history of computing and process engineering as the grounding for how to develop and behave in processes, you offload a huge amount of the work in getting software that’s “right” for the domain you’re working in. But not being aware of them and being heedless that the techniques hard won were hard won by people at least or more smart than you facing similar problems is leading to a cycle in software that’s needlessly dumb, making stupid mistakes that are unnecessary.
    There was a great Star Trek NG episode where Picard is stranded on a planet with a creature that can only speak in metaphorical language. Every sentence it uses refers to an event in the past and you have to understand it’s history to understand it today. Because LLMs are entirely trained on historical corpus, there is no time in history when all the techniques and processes and system design thinking was more relevant. Like that episode, Darmok, you can elicit a wealth of experience by simply referring to a technique from the past - if you know what it is.
    Another way to put it , those that aren’t aware of their history are doomed to repeat it. The sad part of the situation is the coding agent you’re working with is fully trained on it, but unless you intentionally activate the semantic space and bring the concepts into its J-space you won’t maximize the value of that corpus. So, we are using these tools which are mostly crap duct-taped together, which suffer from flaws well understood for decades, mostly because of the driving human being ignorant of the available corpus.
3. weberer · 1789777316 · focus · HN ↗
  Its like the Epic Games Store supporting Linux, or [any website] supporting dark mode. You'd think its an easy to implement bare minimum that everyone asks for, but its like pulling teeth to actually get it done.
  1. mitxela · 1789785977 · focus · HN ↗
    Linux is basically impossible to support. Valve pulled it off by shipping a complete copy of Ubuntu 12.02 with Steam.
    grim_io · 1789800945 · focus · HN ↗
    Where does Valve use Ubuntu? SteamOS is Arch.
    acrispino · 1789809301 · focus · HN ↗
    <a href="https://gitlab.steamos.cloud/steamrt/scout/sdk" rel="nofollow">https://gitlab.steamos.cloud/steamrt/scout/sdk
    dns_snek · 1789811136 · focus · HN ↗
    <Platform> is basically impossible to support. <Company> pulled it off by shipping a complete copy of the Chromium browser with <Product> and turning it into a web application.
    In any case I don't see how this is materially different from Windows where it's the norm for every game to ship its own libraries and install various redistributables to function.
    mitxela · 1789822276 · focus · HN ↗
    On Windows those libraries are part of the application package. On Linux they're supposedly part of the OS, they're designed to be part of the OS and the loader is trying to get them from the OS, but is redirected to get them from the wrapper layer provided by the store (neither the application nor the OS!) instead.
  2. x______________ · 1789813526 · focus · HN ↗
    > ..or [any website] supporting dark mode. You'd think its an easy to implement bare minimum that everyone asks for, but its like pulling teeth to actually get it done.
    At least with dark mode, you can ignore most web developers and get a browser extension to make everything dark, then only webmasters who don't follow standards gets it wrong.

Open on Hacker News to reply ↗

Unofficial Hacker News client; not affiliated with Y Combinator.